MLOps.community cover image

Explainability in the MLOps Cycle // Dattaraj Rao // MLOps Podcast #138

MLOps.community

00:00

L L M's Are Not Enough for a Task

Large language models, while they're interesting may not necessarily be sufficient for a task because of the context that's required. We saw some like one of the examples we had was this text research. It was giving the relevant answers, but we could not justify how it would be like a tax rule. So in that use case, what really worked for us would be we wanted to extract specific entities like which county had how much person text and what was the what was the imposition type. And then the key thing is building a knowledge graph. Because as a relation, it gets very complex.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
 Get the app